Search Results - "Picheny, M.A."

The IBM expressive text-to-speech synthesis system for American English by Pitrelli, J.F., Bakis, R., Eide, E.M., Fernandez, R., Hamza, W., Picheny, M.A.

“…Expressive text-to-speech (TTS) synthesis should contribute to the pleasantness, intelligibility, and speed of speech-based human-machine interactions which…”
Get full text

Decision trees for phonological rules in continuous speech by Bahl, L.R., deSouza, P.V., Gopalakrishnan, P.S., Nahamoo, D., Picheny, M.A.

“…The authors present an automatic method for modeling phonological variation using decision trees. For each phone they construct a decision tree that specifies…”
Get full text

Towards Pooled-Speaker Concatenative Text-to-Speech by Eide, E.M., Picheny, M.A.

“…In this paper we explore the merging of data from various speakers in building a concatenative text-to-speech system. First, we investigate the pooling of data…”
Get full text

On a model-robust training method for speech recognition by Nadas, A., Nahamoo, D., Picheny, M.A.

“…Training methods for designing better decoders are compared. The training problem is considered as a statistical parameter estimation problem. In particular,…”
Get full text

Robust methods for using context-dependent features and models in a continuous speech recognizer by Bahl, L.R., de Souza, P.V., Gopalakrishnan, P.S., Nahamoo, D., Picheny, M.A.

“…In this paper we describe the method we use to derive acoustic features that reflect some of the dynamics of frame-based parameter vectors. Models for such…”
Get full text

Rapid likelihood calculation of subspace clustered Gaussian components by Aiyer, A., Gales, M.J.F., Picheny, M.A.

“…In speech recognition systems, computing the likelihoods of the acoustic models is an intensive task. One approach to reduce this cost is to use subspace…”
Get full text

Context dependent phonetic duration models for decoding conversational speech by Monkowski, M.D., Picheny, M.A., Srinivasa Rao, P.

“…Conversational speech provides a particularly difficult task for speech recognition. It provides much more variability than either dictation, read speech, or…”
Get full text

Adaptive labeling: normalization of speech by adaptive transformations based on vector quantization by Nadas, A., Nahamoo, D., Picheny, M.A.

“…A general technique termed adaptive labeling is presented for the normalization of the speech signal. In principle, adaptive labeling is applicable to any…”
Get full text

Speech recognition using noise-adaptive prototypes by Nadas, A., Nahamoo, D., Picheny, M.A.

“…A probabilistic mixture model is described for a frame (the short-term spectrum) of each to be used in speech recognition. Each component of the mixture is…”
Get full text

Speaker clustering and transformation for speaker adaptation in large-vocabulary speech recognition systems by Padmanabhan, M., Bahl, L.R., Nahamoo, D., Picheny, M.A.

“…A speaker adaptation strategy is described that is based on finding a subset of speakers, from the training set, who are acoustically close to the test…”
Get full text

Experiments using data augmentation for speaker adaptation by Bellegarda, J.R., de Souza, P.V., Nahamoo, D., Padmanabhan, M., Picheny, M.A., Bahl, L.R.

“…Speaker adaptation typically involves customizing some existing (reference) models in order to account for the characteristics of a new speaker. This work…”
Get full text

A channel-bank-based phone detection strategy by Gopalakrishnan, P.S., Nahamoo, D., Padmanabhan, M., Picheny, M.A.

“…This paper presents a channel-bank based phone detection algorithm, that can be used in greatly cut down the search space in the process of mapping a set of…”
Get full text

Decoder selection based on cross-entropies by Gopalakrishnan, P.S., Kanevsky, D., Nadas, A., Nahamoo, D., Picheny, M.A.

“…The authors generalize the maximum likelihood and related optimization criteria for training and decoding with a speech recognizer. The generalizations are…”
Get full text

Acoustic Markov models used in the Tangora speech recognition system by Bahl, L.R., Brown, P.F., de Souza, P.V., Picheny, M.A.

“…The Speech Recognition Group at IBM Research has developed a real-time, isolated-word speech recognizer called Tangora, which accepts natural English sentences…”
Get full text

Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task by Bahl, L.R., Balakrishnan-Aiyer, S., Bellgarda, J.R., Franz, M., Gopalakrishnan, P.S., Nahamoo, D., Novak, M., Padmanabhan, M., Picheny, M.A., Roukos, S.

“…In this paper we discuss various experimental results using our continuous speech recognition system on the Wall Street Journal task. Experiments with…”
Get full text

An iterative 'flip-flop' approximation of the most informative split in the construction of decision trees by Nadas, A., Nahamoo, D., Picheny, M.A., Powell, J.

“…The authors seek a fast algorithm for finding the best question to ask (i.e., best split of predictor values) about a predictor variable when predicting…”
Get full text

Context dependent vector quantization for continuous speech recognition by Bahl, L.R., de Souza, P.V., Gopalakrishnan, P.S., Picheny, M.A.

“…The authors present a method for designing a vector quantizer for speech recognition that uses decision networks constructed by examining the phonetic context…”
Get full text

Speaker clustering and transformation for speaker adaptation in speech recognition systems by Padmanabhan, M., Bahl, L.R., Nahamoo, D., Picheny, M.A.

“…A speaker adaptation strategy is described that is based on finding a subset of speakers, from the training set, who are acoustically close to the test…”
Get full text

Automatic phonetic baseform determination by Bahl, L.R., Das, S., deSouza, P.V., Epstein, M., Mercer, R.L., Merialdo, B., Nahamoo, D., Picheny, M.A., Powell, J.

“…The authors describe a series of experiments in which the phonetic baseform is deduced automatically for new words by utilizing actual utterances of the new…”
Get full text

Speech recognition using noise-adaptive prototypes by Nadas, A., Nahamoo, D., Picheny, M.A.

“…A probabilistic mixture mode is described for a frame (the short term spectrum) of speech to be used in speech recognition. Each component of the mixture is…”
Get full text